Poisoning attacks on machine learning models in cyber systems and mitigation strategies

Rauf Izmailov; Sridhar Venkatesan; Achyut Reddy; Ritu Chadha; Michael De Lucia; Alina Oprea

doi:10.1117/12.2622112

30 May 2022 Poisoning attacks on machine learning models in cyber systems and mitigation strategies

Rauf Izmailov, Sridhar Venkatesan, Achyut Reddy, Ritu Chadha, Michael De Lucia, Alina Oprea

Proceedings Volume 12117, Disruptive Technologies in Information Sciences VI; 1211702 (2022) https://doi.org/10.1117/12.2622112
Event: SPIE Defense + Commercial Sensing, 2022, Orlando, Florida, United States

Abstract

Poisoning attacks on training data are becoming one of the top concerns among users of machine learning systems. The goal of such attacks is to inject a small set of maliciously mislabeled training data into the training pipeline so as to detrimentally impact a machine learning model trained on such data. Constructing such attacks for cyber applications is especially challenging due to their realizability constraints. Furthermore, poisoning mitigation techniques for such applications are also not well understood. This paper investigates techniques for realizable data poisoning availability attacks (using several cyber applications), in which an attacker can insert a set of poisoned samples at the training time with the goal of degrading the accuracy of the deployed model. We design a white-box, realizable poisoning attack that degraded the original model’s accuracy by generating mislabeled samples in close vicinity of a selected subset of training points. We investigate this strategy and its modifications for key classifier architectures and provide specific implications for each of them. The paper also proposes a novel data cleaning method as a defense against such poisoning attacks. Our defense includes a diversified ensemble of classifiers, each trained on a different subset of the training set. We use the disagreement of the classifiers’ predictions as a decision whether to keep a given sample in the training dataset or remove it. The results demonstrate the efficiency of this strategy with very limited performance penalty.

Conference Presentation

Citation Download Citation

Rauf Izmailov, Sridhar Venkatesan, Achyut Reddy, Ritu Chadha, Michael De Lucia, and Alina Oprea "Poisoning attacks on machine learning models in cyber systems and mitigation strategies", Proc. SPIE 12117, Disruptive Technologies in Information Sciences VI, 1211702 (30 May 2022); https://doi.org/10.1117/12.2622112

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available